From 151b383fe1137e0de1d0308004a1446ad46a1ff9 Mon Sep 17 00:00:00 2001 From: EGA-SUPREMO Date: Sun, 19 May 2024 11:53:01 -0400 Subject: [PATCH] add regex for video webpage url --- yt_dlp/extractor/cablecasttv.py | 35 +++++++++++++-------------------- 1 file changed, 14 insertions(+), 21 deletions(-) diff --git a/yt_dlp/extractor/cablecasttv.py b/yt_dlp/extractor/cablecasttv.py index 6f35d2e108..0dd6828442 100644 --- a/yt_dlp/extractor/cablecasttv.py +++ b/yt_dlp/extractor/cablecasttv.py @@ -13,35 +13,28 @@ class CableCastTVIE(InfoExtractor): 'ext': 'mp4', 'title': 'Village Board Meeting 4/24/24', }, - }, { - 'url': 'https://fyptt.to/10382/beautiful-livestream-tits-and-nipples-slip-from-girls-who-loves-talking-with-their-viewers/', - 'only_matching': True, - }, { - 'url': 'https://fyptt.to/120/small-tits-fit-blonde-dancing-naked-at-the-front-door-on-tiktok', - 'only_matching': True, - }, { - 'url': 'https://fkbae.to/18', - 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + with open('output.txt', 'w', encoding='utf-8') as file: + file.write(webpage) + + + url_video_webpage = self._html_search_regex(r']*class=\"trms-player\"[^>]*src=\"([^\"]+)\"', webpage, 'url_video_webpage') + webpage_video = self._download_webpage(url_video_webpage, video_id) + + video_url = self._html_search_regex(r'"([^\"]*\.m3u8)"', webpage_video, 'video URL') + print(video_url) + formats = [] - format_url = self._html_search_regex(r'"embedURL":"([^"]+)"', webpage, 'video URL') - format_url = re.sub(r'\\', '', format_url) + formats.extend(self._extract_m3u8_formats(video_url, video_id, ext='mp4', m3u8_id='hls')) + print(formats) + #format_url = re.sub(r'\\', '', format_url) - webpage_video = self._download_webpage(format_url, video_id) - - match = re.search(r'(https:\/\/[^"]+\.mp4)', webpage_video) - format_url = match.group(1) - formats.append({ - 'url': format_url, - 'format_id': 'default', - }) - - title = self._html_search_regex(r'(.+?)', webpage, 'title') + title = self._html_search_regex(r'(.+?)', webpage, 'title') # base_url = re.search(r'^(https?://[a-zA-Z0-9_-]+\.to)', url).group(1) # http_headers = {'Referer': base_url}